Product & Planning

vtmocanu Skill

Creates documentation-first PRDs (a short forge issue plus a detailed prds/ file with milestones), then offers to start work, commit for later, or send the PRD to uzi. Use when the user wants to create a PRD, spec out a new feature, write a product requirements document, or turn a feature idea into a tracked GitHub/GitLab/Forgejo issue. Triggers include "create a PRD", "new PRD", "/prd-create", "write a PRD for", "spec this feature".

vtmocanu Bundle

Create a git worktree for PRD work with a descriptive branch name. Infers PRD from context or asks user.

vtmocanu Skill

Update PRD progress based on git commits and code changes, enhanced by conversation context

vtmocanu Skill

Update PRD based on design decisions and strategic changes made during conversations

wellcaffeinated Skill

Daily-note processing — works through unprocessed daily notes, extracts anything in the prose worth capturing permanently, files it to the right home, and marks each note processed. Use when processing journal backlog, after a stretch of daily note capture, or when the user asks to "process my daily notes" / "catch up on my journal". Read-only unless the user approves proposed actions.

wp-media Skill

Orchestrated audit of the current repo's open GitHub-issue backlog — fans out code-review and per-issue categorization agents, verifies which issues are already fixed, and produces a ranked shortlist of AI-autonomous quality wins plus a full triage (Should Keep / Already Fixed / Unsure / Close Candidate), published as an HTML artifact. Read-only against GitHub — never closes, comments on, or edits issues.

zhengyunhui123-dev Bundle

产品规划总控 skill。用于做产品规划、从需求调研到功能清单再到开发/原型规划的轻量编排；根据用户目标决定调用 product-requirements-researcher、project-feature-list-generator、project-development-planner 等产品规划相关 skill。统一要求产物保存到当前项目的“项目管理”目录，不单独创建 projects 工作目录；不做调研统计文档，只在必要时保存调用报告和功能清单。Use when the user wants lightweight product planning orchestration, deciding which planning skills to use, coordinating requirement research, feature lists, prototypes, PRD, or development planning.

zhengyunhui123-dev Bundle

通过深度、迭代式访谈收集软件需求并生成正式调研报告。Use when the user wants 需求调研、需求访谈、澄清需求、产品规划、写 PRD、设计产品、需求分析、生成调研报告；也用于 AI 开发前的 0-1 项目/产品/模块建设启动，当用户只给出模糊想法而要求开始开发时，先用 AskUserQuestion 访谈澄清，判断是 AI 直接开发还是实地调研考察，再形成足以转化为功能的需求调研报告。

chieaid24 Bundle

Full pipeline entry point for a new feature or change: interrogate the idea (sharpening domain language, writing ADRs as decisions crystallize), then route by scope - publish a [PRD] issue with child work slices for large features, or go straight to one or a few dependency-linked issues for small changes. Both converge on the same issue-creation flow. Use when starting from a rough idea toward a dependency-linked issue queue.

cuellarfr Bundle

Plan, conduct, and analyze UX research using proven methodologies. Use when planning user research, writing interview scripts, creating test plans, recruiting participants, analyzing qualitative data, or synthesizing findings into actionable insights. Covers generative, evaluative, and continuous discovery research with specific frameworks, scoring rubrics, and templates.

cuellarfr Bundle

Connect design decisions to business outcomes through competitive analysis, opportunity mapping, Jobs to Be Done, outcome-driven discovery, value proposition design, and UX metrics. Shape product direction with strategic frameworks grounded in evidence.

daemon-blockint-tech Skill

Orchestrate 100+ specialized AI agents across an ensemble of frontier and distilled models to discover, debate, validate, prove, enrich, and triage exploitable bugs end-to-end. Use when the user wants to run the full MDASH pipeline with multi-model ensemble, dynamic agent spawning, or production-scale vulnerability discovery. Every finding terminates at a tool oracle (𝒯), classical-ML detector (𝓜), or scored hypothesis (𝓛), and ships with D3FEND defensive techniques, ATT&CK offensive context, exposure scoring, and DevSecOps routing.

daemon-blockint-tech Skill

Scaffold a research-grade experiment that tests whether a Looped / Recurrent-Depth Transformer (RDT) is better than a parameter-matched vanilla transformer at vulnerability discovery, when both are continued-pretrained on a security corpus. Use when the user says "test the looped-transformer hypothesis", "run the OpenMythos RDT experiment", "compare loop count to trial budget", "does inference-time loops help security reasoning", or asks for a reproducible research pipeline around the Mythos architecture hypothesis. The skill scaffolds the experiment — it does NOT make claims about Mythos itself, and it explicitly bins OpenMythos as a community speculative reconstruction, not Anthropic's actual model.

aws-samples Bundle

Use when investigating what AWS services are running, checking fleet health by service tag, responding to "what's in my account" questions, onboarding to a new AWS account, or preparing an environment overview. Uses tag-based Fleet Intelligence: discovers tag taxonomy, aggregates resource counts by service tag, and checks alarm status — does NOT enumerate individual resources.

bendemartin97 Skill

Builds a weekly content plan for the week from content pillars, the idea backlog, and upcoming occasions, and creates the tasks in the connected task tool. Use when the week needs planning, a weekly content plan needs to be created, or you need to decide what gets produced next.

fxckcode Bundle

Systematic codebase audit — gap analysis against specs (PRD/SDD), architecture review, code quality assessment, and migration readiness checks. Use when the user asks to review a codebase, compare it to a spec, or assess a project.

fxckcode Bundle

Behavioral protocol for intelligently loading external project folders as reference context. Registers paths via config file, --add-dir, or in-prompt declaration, then runs a 6-pass heuristic discovery to select the most relevant files within a strict budget (15 files max). Trigger: When user says "@context", "reference path", "reference folder", "reference project", "use as context", "add context from", "load context", "path context", "contexto de", "referenciar", "cargar contexto".

gmarmat Skill

[PM Twin] Simulate persona panels (synthetic voice-of-customer) to pressure-test a PRD/UX/feature before real research. Critical, adversarial answers — not a cheerleading session. Never a substitute for real users. Pairs with /userstudy.

gmarmat Skill

[PM Twin] Generate or update product roadmap from PRD phases and feature index.

gmarmat Skill

[PM Twin] Load pm-kit context — reads PRD, arch, skill catalog, sibling-kit availability, and any new upstream commits since your last session.

gmarmat Skill

[PM Twin] Generate user research plan and interview script from PRD — discovery, usability, or feedback studies.

gmarmat Skill

[PM Twin] Generate product status update from recent activity — git history, feature progress, metrics.

hardness1020 Bundle

Create PRDs with success metrics for Stage A of the VibeFlow docs-first workflow

hardness1020 Bundle

Codebase discovery and analysis for Stage B of the VibeFlow docs-first workflow

hebstr Bundle

User-invocable ONLY via `/audit:walkthrough`. Does not auto-trigger on mentions of "review", "review findings", "review report", "walk through", "walkthrough", "go through one by one", "triage", "DEFERRED.md", "revisit deferred", or French equivalents ("revue", "passer en revue", "trier", "reprendre les findings", "revoir les éléments différés"). Interactive, point-by-point walkthrough of a review report produced by any Claude Code review skill (skill-adversary, critical-code-reviewer, or any other). Three modes: **orchestrator mode** (provide a target + optional `--reviewer` flag: detects deployment context, calibrates severity, launches the reviewer, then walks through its report), **walkthrough-only mode** (processes an existing report from the conversation), and **revisit-deferred mode** (processes the project's `DEFERRED.md` backlog as the input source). Parses review findings and processes each one at a time: re-evaluates validity, proposes and applies fixes, checks impacted files for regressions, and w

hieutrtr Skill

Phase-0 spike probe used to verify Claude Code skill discovery and triggering. Trigger ONLY when the user message contains the literal phrase "hello-test ping" — no paraphrases, no partial matches. Output is a single fixed acknowledgement string with the current ISO-8601 UTC timestamp, produced by running a one-liner Bash command. Do NOT trigger on the words "hello", "test", "ping" individually, on phrases like "hello world", "say hello", "ping me", or any other variant. This skill exists purely as a fingerprint for the auto-test-skills repo Phase 0 spike to confirm that user-level skills dropped at ~/.claude/skills/<name>/SKILL.md are auto-discovered. Safe to delete after Phase 0 sign-off.

idimsh Skill

Use when the user wants to design a business model, validate a venture idea, or create a structured business plan. Triggered by requests like "think through a business idea", "business model", "validation plan", "Business Design", "Geschäftsidee durchdenken", "Business Model erstellen", or when a venture needs a structured thesis, Lean Canvas, hypotheses, roadmap, and decision matrix.

lavidrori0702 Bundle

Renders the interactive HTML demo (mock.html) for the tableau-dashboard-plugin workflow at the plan's screen size, populated from the real sample CSVs, so the analyst can share a realistic demo and validate direction before any Tableau work. Builds strictly from DASHBOARD-PLAN.md — every KPI, chart, filter, and interaction — and ends with a coverage checklist proving each plan element (screen size, every filter, every interaction) was rendered, so omissions are visible before the stakeholder sees it. Enforces readable slot sizing (no compressed, out-of-bounds, or empty-space-heavy charts). Reads DASHBOARD-PLAN.md and the sample CSVs, and DESIGN-TOKENS.md if present. Use when the user wants to build the mock, render the demo, or when tableau-route reports mock is next. Step 6 of 8 in the workflow.

lavidrori0702 Bundle

Produces the strict DASHBOARD-PLAN.md for the tableau-dashboard-plugin workflow — the complete blueprint tableau-mock and tableau-build build against. Decides screen size here (so slot sizing is correct downstream), lays out a grid of named slots, and assigns every KPI, chart, filter, and interaction a stable id that later steps reference. Reads DATA-MODEL.md (field names) and, if present, PRD.md and DESIGN-TOKENS.md; proposes extra KPIs and patterns beyond the literal request. Use when the user wants to plan the dashboard, lay out KPIs/charts/filters, or when tableau-route reports plan is next. Step 5 of 8 in the workflow.

mataeil Skill

Score GitHub Issues using the RICE framework and propose a priority ordering. Strategize phase skill — turns raw issues into a ranked action plan written to agent/state/backlog.json.

microsoft Skill

Design a Power Platform solution through adaptive discovery and a Power CAT-style architecture review. Recommend a composed solution across Canvas, model-driven apps, Power Pages, code apps, managed apps, Copilot Studio, Dataverse, Power Automate, and Power BI. Explain fit, tradeoffs, security, compliance, ALM, implementation, learning, certifications, and curated build resources. Offer focused follow-up detail or a complete Architecture Delivery Pack. Use for: "design architecture for my Power Platform scenario", "what should I build", "recommend a Power Platform pattern", "code apps vs managed apps", "should this be a Copilot Studio agent", "Power CAT style architecture review", or "solution blueprint".

milkywayrules Bundle

Multi-model fusion for exploration and decision support. Use when the user asks to "fuse", "fusion", "multi-model", "ask several models", runs /verasic-fusion, or wants board-verdict, rfc-review, tradeoff-matrix, brief-research, risk-register, devils-advocate, premortem, stakeholder-lens, or compare-to-status-quo templates across named models (e.g. composer-2.5-fast, glm-5.2-high, gemini-3-flash).

morluto Bundle

Investigate MCP tool availability, discovery, and selection, including controlled adoption evaluations.

mornikar Bundle

内容输出专家（v3 高解耦架构）。可独立运行或作为编排流程的一部分。 负责撰写PRD、技术文档、用户手册、汇报材料。输出结构清晰、表达准确的专业文档。 独立模式：直接接收文档撰写需求，输出文档 编排模式：由 pm-runner 调度，可被 pm-coder 委托 触发词：文档、PRD、撰写、编写、手册、说明、汇报、纪要、CHANGELOG、写文档

mornikar Bundle

需求池管理专家（v3 高解耦架构）。可独立运行或作为编排流程的一部分。 负责需求池管理、优先级排序、分批交付计划、MVP定义。 是整个工作流的 Phase 0 守门人。 独立模式：直接接收需求列表，排序+MVP定义 编排模式：由 orchestrator 触发 Phase 0 触发词：需求池、优先级排序、MVP定义、需求管理、批次规划、需求收集、排优先级

mrvladd-d Skill

Bootstrap a Memory Bank for a new or existing repository, then route into PRD-driven or brownfield workflows.